© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7731
    Prev
    Next
    INDEX
    Explanations

    guide-like content offering assistance or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating guidance or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boycot
    -0.69
     disliked
    -0.69
     liking
    -0.69
    cakes
    -0.65
     wearing
    -0.65
    ween
    -0.65
     kisses
    -0.64
     stealing
    -0.64
    Offline
    -0.63
     staged
    -0.62
    POSITIVE LOGITS
     summarize
    1.50
     eluc
    1.42
     summar
    1.36
     explain
    1.26
     enlight
    1.25
     clarify
    1.25
     illustrate
    1.25
     outline
    1.22
     summarizes
    1.21
     illuminate
    1.19
    Activations Density 0.250%

    No Known Activations